Combining probability model initializations of multiple reference frames

Abstract

An example method of video decoding includes receiving a video bitstream comprising a plurality of frames and identifying a plurality of reference frames for a current frame of the plurality of frames. The method also includes obtaining respective contexts for the plurality of reference frames and initializing a current frame context for the current frame by performing a weighted average of the respective contexts using a set of respective weights. The set of respective weights may comprise fixed weights. The method further includes entropy decoding one or more syntax elements for the current frame using the current frame context and reconstructing the current frame using the one or more syntax elements.

What is claimed is: 
     
         1 . A method of video decoding performed at a computing system having memory and one or more processors, the method comprising:
 receiving a video bitstream comprising a plurality of frames;   identifying a plurality of reference frames for a current frame of the plurality of frames;   obtaining respective contexts for the plurality of reference frames;   initializing a current frame context for the current frame by performing a weighted average of the respective contexts using a set of respective weights, wherein the set of respective weights comprises fixed weights;   entropy decoding one or more syntax elements for the current frame using the current frame context; and   reconstructing the current frame using the one or more syntax elements.   
     
     
         2 . The method of  claim 1 , wherein the fixed weights comprise a first weight of ⅞ and a second weight of ⅛. 
     
     
         3 . The method of  claim 1 , wherein the fixed weights correspond to a predefined weighting factor. 
     
     
         4 . The method of  claim 3 , wherein the predefined weighting factor is proportional to a distance between the current frame and a reference frame. 
     
     
         5 . The method of  claim 3 , further comprising selecting the predefined weighting factor from a plurality of predefined weighting factors. 
     
     
         6 . The method of  claim 5 , wherein the predefined weighting factor is selected based on an indicator signaled in a high-level syntax. 
     
     
         7 . The method of  claim 5 , wherein the plurality of predefined weighting factors comprises a ½ weighting factor, a ¾ weighting factor, and a ⅞ weighting factor. 
     
     
         8 . The method of  claim 1 , wherein the set of respective weights comprises a first weight assigned to a first reference frame and a second weight assigned to a second reference frame. 
     
     
         9 . The method of  claim 8 , wherein the first reference frame is closer to the current frame than the second reference frame, and wherein the first weight is larger than the second weight. 
     
     
         10 . The method of  claim 1 , wherein the current frame context corresponds to a first set of syntax elements that includes the one or more syntax elements; and
 the method further comprises initializing a second current frame context for the current frame by performing a second weighted average of the respective contexts using a second set of respective weights.   
     
     
         11 . The method of  claim 10 , wherein the first set of respective weights comprises a set of unequal weights, and wherein the second set of respective weights comprises a set of equal weights. 
     
     
         12 . The method of  claim 10 , wherein the second set of respective weights are signaled in the video bitstream or are derived at a decoding component. 
     
     
         13 . The method of  claim 1 , wherein the one or more syntax elements comprise one or more motion vector-related syntax elements. 
     
     
         14 . The method of  claim 1 , wherein the respective contexts for the plurality of reference frames are obtained based on coded information. 
     
     
         15 . The method of  claim 1 , further comprising selecting a set of reference frames from the plurality of reference frames, wherein the respective contexts correspond to the set of reference frames. 
     
     
         16 . A method of video encoding performed at a computing system having memory and one or more processors, the method comprising:
 receiving video data comprising a plurality of frames;   identifying a plurality of reference frames for a current frame of the plurality of frames;   obtaining respective contexts for the plurality of reference frames;   initializing a current frame context for the current frame by performing a weighted average of the respective contexts using a set of respective weights, wherein the set of respective weights comprises fixed weights; and   entropy encoding one or more syntax elements for the current frame using the current frame context.   
     
     
         17 . The method of  claim 16 , further comprising signaling the one or more entropy-encoded syntax elements and the current frame in a video bitstream. 
     
     
         18 . The method of  claim 16 , further comprising signaling the obtained respective contexts in a video bitstream. 
     
     
         19 . A non-transitory computer-readable storage medium storing a video bitstream that is generated by a video encoding method, the video encoding method comprising:
 receiving video data comprising a plurality of frames;   identifying a plurality of reference frames for a current frame of the plurality of frames;   obtaining respective contexts for the plurality of reference frames;   initializing a current frame context for the current frame by performing a weighted average of the respective contexts using a set of respective weights, wherein the set of respective weights comprises fixed weights; and   generating entropy-encoded syntax elements by entropy encoding one or more syntax elements for the current frame using the current frame context; and   wherein the video bitstream comprises the encoded current frame and the entropy-encoded syntax elements.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 19 , wherein the video bitstream includes an indicator indicating the plurality of reference frames.